metacrunch-marcxml 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +24 -0
- data/.rspec +3 -0
- data/.travis.yml +9 -0
- data/.yardopts +9 -0
- data/Gemfile +17 -0
- data/License.txt +22 -0
- data/Rakefile +6 -0
- data/Readme.md +92 -0
- data/bin/console +14 -0
- data/lib/metacrunch/marcxml/document/controlfield.rb +17 -0
- data/lib/metacrunch/marcxml/document/datafield.rb +50 -0
- data/lib/metacrunch/marcxml/document/datafield_set.rb +39 -0
- data/lib/metacrunch/marcxml/document/subfield.rb +17 -0
- data/lib/metacrunch/marcxml/document/subfield_set.rb +42 -0
- data/lib/metacrunch/marcxml/document.rb +111 -0
- data/lib/metacrunch/marcxml/parser.rb +81 -0
- data/lib/metacrunch/marcxml/version.rb +5 -0
- data/lib/metacrunch/marcxml.rb +38 -0
- data/metacrunch-marcxml.gemspec +24 -0
- metadata +104 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 108b2f6697c4cc1fd07f61231da1a5b0219e7fe1
|
4
|
+
data.tar.gz: 8ca7bdf5edc53577c1dd700e00af500b388bb386
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 80c1d9f509ee566035a76f62429662fd524d4f123b50a303776aea4e301479ad41c380e89f9622d3063b96733fec6fdaf72b4ce146ca027a7ef07836dc6e55b1
|
7
|
+
data.tar.gz: dd1abb2e6f24dd197ffdcb3b8e1b774d127d9b5a3fc13cb7e464f5e6fcb1ffa83f8054bef2a132ce4fed31236333947d6be3970d6047b59621a38417c1616bab
|
data/.gitignore
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
.DS_Store
|
2
|
+
/doc
|
3
|
+
*.gem
|
4
|
+
*.rbc
|
5
|
+
.bundle
|
6
|
+
.config
|
7
|
+
.yardoc
|
8
|
+
Gemfile.lock
|
9
|
+
InstalledFiles
|
10
|
+
_yardoc
|
11
|
+
coverage
|
12
|
+
doc/
|
13
|
+
lib/bundler/man
|
14
|
+
pkg
|
15
|
+
rdoc
|
16
|
+
spec/reports
|
17
|
+
test/tmp
|
18
|
+
test/version_tmp
|
19
|
+
tmp
|
20
|
+
*.bundle
|
21
|
+
*.so
|
22
|
+
*.o
|
23
|
+
*.a
|
24
|
+
mkmf.log
|
data/.rspec
ADDED
data/.travis.yml
ADDED
data/.yardopts
ADDED
data/Gemfile
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
source "https://rubygems.org"
|
2
|
+
|
3
|
+
gemspec
|
4
|
+
|
5
|
+
group :development do
|
6
|
+
gem "bundler", ">= 1.15"
|
7
|
+
gem "rake", ">= 12.1"
|
8
|
+
gem "rspec", ">= 3.5.0", "< 4.0.0"
|
9
|
+
|
10
|
+
if !ENV["CI"]
|
11
|
+
gem "pry-byebug", ">= 3.5.0"
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
group :test do
|
16
|
+
gem "simplecov", ">= 0.15.0"
|
17
|
+
end
|
data/License.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2017 René Sprotte
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
data/Readme.md
ADDED
@@ -0,0 +1,92 @@
|
|
1
|
+
metacrunch-marcxml
|
2
|
+
==================
|
3
|
+
|
4
|
+
[![Build Status](https://travis-ci.org/ubpb/metacrunch-marcxml.svg)](https://travis-ci.org/ubpb/metacrunch-marcxml)
|
5
|
+
[![Code Climate](https://codeclimate.com/github/ubpb/metacrunch-marcxml/badges/gpa.svg)](https://codeclimate.com/github/ubpb/metacrunch-marcxml)
|
6
|
+
|
7
|
+
This is the official [MARCXML](http://www.loc.gov/standards/marcxml/) package for the [metacrunch ETL toolkit](https://github.com/ubpb/metacrunch). It allows you to access MARCXML data by a simple and powerful Ruby API.
|
8
|
+
|
9
|
+
There is no runtime dependency to metacrunch, so it's fine to use this gem in any Ruby application where you need to access MARCXML data.
|
10
|
+
|
11
|
+
*Note: Before 2.0 this package was incorrectly named `metacrunch-mab2` and has been renamed to `metacrunch-marcxml`. Due to this renaming and further development there are breaking API changes if you upgrade from 1.x to 2.x.*
|
12
|
+
|
13
|
+
|
14
|
+
Installation
|
15
|
+
------------
|
16
|
+
|
17
|
+
Include the gem in your `Gemfile`
|
18
|
+
|
19
|
+
```ruby
|
20
|
+
gem "metacrunch-marcxml", "~> 2.0.0"
|
21
|
+
```
|
22
|
+
|
23
|
+
and run `$ bundle install` to install it.
|
24
|
+
|
25
|
+
Or install it manually
|
26
|
+
|
27
|
+
```
|
28
|
+
$ gem install metacrunch-marcxml
|
29
|
+
```
|
30
|
+
|
31
|
+
|
32
|
+
Usage example
|
33
|
+
-------------
|
34
|
+
|
35
|
+
**Loading the library**
|
36
|
+
```ruby
|
37
|
+
require "metacrunch/marcxml"
|
38
|
+
```
|
39
|
+
|
40
|
+
**Parsing a [MARCXML file](http://d-nb.info/982392028/about/marcxml)**
|
41
|
+
```ruby
|
42
|
+
# Load a MARCXML file (from a remote location in this example).
|
43
|
+
require "open-uri"
|
44
|
+
marcxml = open("http://d-nb.info/982392028/about/marcxml"){|io| io.read}
|
45
|
+
|
46
|
+
# Now parse the file
|
47
|
+
document = Metacrunch::Marcxml.parse(marcxml)
|
48
|
+
# .. or use the convenience method
|
49
|
+
document = Metacrunch::Marcxml(marcxml)
|
50
|
+
```
|
51
|
+
|
52
|
+
**Accessing control fields**
|
53
|
+
```ruby
|
54
|
+
controlfield = document.controlfield("005")
|
55
|
+
# same as ...
|
56
|
+
controlfield = document.controlfield(5)
|
57
|
+
# => #<Metacrunch::Marcxml::Document::Controlfield:0x007fd4c5120ec0 ...>
|
58
|
+
|
59
|
+
tag = controlfield.tag
|
60
|
+
# => "005"
|
61
|
+
value = controlfield.value
|
62
|
+
# => "20130926112144.0"
|
63
|
+
```
|
64
|
+
|
65
|
+
**Accessing data fields / sub fields**
|
66
|
+
```ruby
|
67
|
+
# Find fields matching tag=100 and indicator1=1 (author)
|
68
|
+
datafield_set = document.datafields(100, ind1: "1")
|
69
|
+
# => #<Metacrunch::Marcxml::Document::DatafieldSet:0x007fd4c4ce4b40 ...>
|
70
|
+
|
71
|
+
first_author = datafield_set.first # set is an Enumerable
|
72
|
+
# => #<Metacrunch::Marcxml::Document::Datafield:0x007fd4c5129480 ...>
|
73
|
+
|
74
|
+
# Get the subfields matching code=a (author name)
|
75
|
+
subfield_set = first_author.subfields("a")
|
76
|
+
# => #<Metacrunch::Marcxml::Document::SubfieldSet:0x007fd4c4c779f0 ...>
|
77
|
+
|
78
|
+
# because sub field "a" is not repeatable we know there can only be one match
|
79
|
+
first_author_subfield = subfield_set.first # subfield_set is an Enumerable
|
80
|
+
# => #<Metacrunch::Marcxml::Document::Subfield:0x007fd4c5129660 ...>
|
81
|
+
|
82
|
+
first_author_name = first_author_subfield.value
|
83
|
+
# => "Orwell, George"
|
84
|
+
|
85
|
+
# ... there is a shortcut for this case
|
86
|
+
first_author_name = document.datafields(100, ind1: "1").subfields("a").first_value
|
87
|
+
```
|
88
|
+
|
89
|
+
License
|
90
|
+
-------
|
91
|
+
|
92
|
+
metacrunch-marcxml is available at [github](https://github.com/ubpb/metacrunch-marcxml) under [MIT license](https://github.com/ubpb/metacrunch-marcxml/blob/master/License.txt).
|
data/bin/console
ADDED
@@ -0,0 +1,50 @@
|
|
1
|
+
module Metacrunch
|
2
|
+
module Marcxml
|
3
|
+
class Document
|
4
|
+
class Datafield
|
5
|
+
|
6
|
+
attr_reader :tag
|
7
|
+
attr_reader :ind1, :ind2
|
8
|
+
|
9
|
+
def initialize(tag, ind1:nil, ind2:nil)
|
10
|
+
@tag = tag
|
11
|
+
@ind1 = ind1
|
12
|
+
@ind2 = ind2
|
13
|
+
@subfields_map = {}
|
14
|
+
end
|
15
|
+
|
16
|
+
#
|
17
|
+
# Returns the sub fields matching the given code.
|
18
|
+
#
|
19
|
+
# @param [String, nil, Array<String>] code of the sub field
|
20
|
+
# @return [Metacrunch::Marcxml::Document::SubfieldSet] sub field with the given code. The set
|
21
|
+
# is empty if the sub field doesn't exists.
|
22
|
+
#
|
23
|
+
def subfields(code = nil)
|
24
|
+
matched_subfields = if code.nil?
|
25
|
+
@subfields_map.values.flatten(1)
|
26
|
+
else
|
27
|
+
if (codes = code).is_a?(Array)
|
28
|
+
codes.map{ |_code| @subfields_map[_code] }.compact.flatten(1)
|
29
|
+
else
|
30
|
+
@subfields_map[code]
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
SubfieldSet.new(matched_subfields)
|
35
|
+
end
|
36
|
+
|
37
|
+
#
|
38
|
+
# Adds a new sub field.
|
39
|
+
#
|
40
|
+
# @param [Metacrunch::Marcxml::Document::Subfield] subfield
|
41
|
+
#
|
42
|
+
def add_subfield(subfield)
|
43
|
+
(@subfields_map[subfield.code] ||= []) << subfield
|
44
|
+
subfield
|
45
|
+
end
|
46
|
+
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
@@ -0,0 +1,39 @@
|
|
1
|
+
module Metacrunch
|
2
|
+
module Marcxml
|
3
|
+
class Document
|
4
|
+
class DatafieldSet
|
5
|
+
include Enumerable
|
6
|
+
|
7
|
+
def initialize(datafields)
|
8
|
+
@datafields = datafields || []
|
9
|
+
end
|
10
|
+
|
11
|
+
def each(&block)
|
12
|
+
@datafields.each(&block)
|
13
|
+
end
|
14
|
+
|
15
|
+
def to_a
|
16
|
+
@datafields
|
17
|
+
end
|
18
|
+
|
19
|
+
def empty?
|
20
|
+
@datafields.empty?
|
21
|
+
end
|
22
|
+
|
23
|
+
def present?
|
24
|
+
!empty?
|
25
|
+
end
|
26
|
+
|
27
|
+
# @return [Metacrunch::Marcxml::Document::SubfieldSet]
|
28
|
+
def subfields(code = nil)
|
29
|
+
subfields = @datafields.map do |datafield|
|
30
|
+
datafield.subfields(code).to_a
|
31
|
+
end.flatten(1)
|
32
|
+
|
33
|
+
Metacrunch::Marcxml::Document::SubfieldSet.new(subfields)
|
34
|
+
end
|
35
|
+
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
@@ -0,0 +1,42 @@
|
|
1
|
+
module Metacrunch
|
2
|
+
module Marcxml
|
3
|
+
class Document
|
4
|
+
class SubfieldSet
|
5
|
+
include Enumerable
|
6
|
+
|
7
|
+
def initialize(subfields)
|
8
|
+
@subfields = subfields || []
|
9
|
+
end
|
10
|
+
|
11
|
+
def each(&block)
|
12
|
+
@subfields.each(&block)
|
13
|
+
end
|
14
|
+
|
15
|
+
def to_a
|
16
|
+
@subfields
|
17
|
+
end
|
18
|
+
|
19
|
+
def empty?
|
20
|
+
@subfields.empty?
|
21
|
+
end
|
22
|
+
|
23
|
+
def present?
|
24
|
+
!empty?
|
25
|
+
end
|
26
|
+
|
27
|
+
def values
|
28
|
+
@subfields.map{ |subfield| subfield.value }
|
29
|
+
end
|
30
|
+
|
31
|
+
def present_values
|
32
|
+
values.map{ |v| v.presence }.compact
|
33
|
+
end
|
34
|
+
|
35
|
+
def first_value
|
36
|
+
present_values[0]
|
37
|
+
end
|
38
|
+
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,111 @@
|
|
1
|
+
require_relative "document/controlfield"
|
2
|
+
require_relative "document/datafield"
|
3
|
+
require_relative "document/datafield_set"
|
4
|
+
require_relative "document/subfield"
|
5
|
+
require_relative "document/subfield_set"
|
6
|
+
|
7
|
+
module Metacrunch
|
8
|
+
module Marcxml
|
9
|
+
class Document
|
10
|
+
|
11
|
+
def initialize
|
12
|
+
@controlfields_map = {}
|
13
|
+
@datafields_map = {}
|
14
|
+
end
|
15
|
+
|
16
|
+
# ------------------------------------------------------------------------------
|
17
|
+
# Control fields
|
18
|
+
# ------------------------------------------------------------------------------
|
19
|
+
|
20
|
+
#
|
21
|
+
# Returns the control field matching the given tag or nil if a control field
|
22
|
+
# with the given tag does not exist.
|
23
|
+
#
|
24
|
+
# @param tag [String, Integer] the tag of the control field. The tag can be
|
25
|
+
# a string or an integer.
|
26
|
+
# @return [Controlfield, nil] the control field with the matching tag or nil
|
27
|
+
# if a control field with a matching tag does not exist.
|
28
|
+
#
|
29
|
+
def controlfield(tag)
|
30
|
+
@controlfields_map[normalize_tag(tag)]
|
31
|
+
end
|
32
|
+
|
33
|
+
#
|
34
|
+
# @!visibility private
|
35
|
+
#
|
36
|
+
def add_controlfield(controlfield)
|
37
|
+
@controlfields_map[controlfield.tag] = controlfield
|
38
|
+
end
|
39
|
+
|
40
|
+
# ------------------------------------------------------------------------------
|
41
|
+
# Data fields
|
42
|
+
# ------------------------------------------------------------------------------
|
43
|
+
|
44
|
+
#
|
45
|
+
# Returns the data fields matching the given tag(s) and/or ind1/ind2.
|
46
|
+
#
|
47
|
+
# @param tag [String, Integer, #each, nil] filter by tag(s). Can be `nil`
|
48
|
+
# to match all data fields. The tag can be a string or an integer. To filter for
|
49
|
+
# more than a single tag, `tag` also accepts any object that responds to `#each` like
|
50
|
+
# `Array` and `Range`.
|
51
|
+
#
|
52
|
+
# @param ind1 [String, nil, Array<String>] filter by indicator 1. Can be nil to match
|
53
|
+
# any indicator.
|
54
|
+
# @param ind2 [String, nil, Array<String>] filter by indicator 2. Can be nil to match
|
55
|
+
# any indicator.
|
56
|
+
#
|
57
|
+
# @return [Metacrunch::Marcxml::Document::DatafieldSet] Set of data fields matching the
|
58
|
+
# given tag(s) and ind1/ind2. The set is empty if a matching field doesn't exist.
|
59
|
+
#
|
60
|
+
def datafields(tag = nil, ind1: nil, ind2: nil)
|
61
|
+
matched_datafields = case tag
|
62
|
+
when nil
|
63
|
+
@datafields_map.values.flatten(1)
|
64
|
+
when Enumerable
|
65
|
+
tag.map{ |_tag| @datafields_map[normalize_tag(_tag)] }.compact.flatten(1)
|
66
|
+
else
|
67
|
+
@datafields_map[normalize_tag(tag)]
|
68
|
+
end
|
69
|
+
|
70
|
+
matched_datafields = (matched_datafields || []).select do |datafield|
|
71
|
+
match_indicator(ind1, datafield.ind1) && match_indicator(ind2, datafield.ind2)
|
72
|
+
end
|
73
|
+
|
74
|
+
DatafieldSet.new(matched_datafields)
|
75
|
+
end
|
76
|
+
|
77
|
+
#
|
78
|
+
# @!visibility private
|
79
|
+
#
|
80
|
+
def add_datafield(datafield)
|
81
|
+
(@datafields_map[datafield.tag] ||= []) << datafield
|
82
|
+
datafield
|
83
|
+
end
|
84
|
+
|
85
|
+
private
|
86
|
+
|
87
|
+
def match_indicator(requested_ind, datafield_ind)
|
88
|
+
[*[requested_ind]].flatten.map do |_requested_ind|
|
89
|
+
if !_requested_ind
|
90
|
+
true
|
91
|
+
elsif _requested_ind == :blank && (datafield_ind == " " || datafield_ind == "-" || datafield_ind.nil?)
|
92
|
+
true
|
93
|
+
elsif _requested_ind == datafield_ind
|
94
|
+
true
|
95
|
+
else
|
96
|
+
false
|
97
|
+
end
|
98
|
+
end.any?
|
99
|
+
end
|
100
|
+
|
101
|
+
def normalize_tag(tag)
|
102
|
+
case tag
|
103
|
+
when Integer then tag.to_s.rjust(3, "0")
|
104
|
+
when String then tag
|
105
|
+
else tag.to_s
|
106
|
+
end
|
107
|
+
end
|
108
|
+
|
109
|
+
end
|
110
|
+
end
|
111
|
+
end
|
@@ -0,0 +1,81 @@
|
|
1
|
+
module Metacrunch
|
2
|
+
module Marcxml
|
3
|
+
class Parser < Ox::Sax
|
4
|
+
|
5
|
+
def parse(mab_xml)
|
6
|
+
# initialize state machine
|
7
|
+
@in_controlfield = @in_datafield = @in_subfield = false
|
8
|
+
|
9
|
+
@controlfield = @datafield = @subfield = nil
|
10
|
+
@document = Document.new
|
11
|
+
@html_entities_coder = HTMLEntities.new
|
12
|
+
|
13
|
+
# convert_special tells ox to convert some html entities already during
|
14
|
+
# parsing, which minifies the amount of entities we have to decode ourself
|
15
|
+
Ox.sax_parse(self, mab_xml, convert_special: true)
|
16
|
+
|
17
|
+
return @document
|
18
|
+
end
|
19
|
+
|
20
|
+
def start_element(name)
|
21
|
+
if name == :subfield
|
22
|
+
@in_subfield = true
|
23
|
+
@subfield = {}
|
24
|
+
elsif name == :datafield
|
25
|
+
@in_datafield = true
|
26
|
+
@datafield = {subfields: []}
|
27
|
+
elsif name == :controlfield
|
28
|
+
@in_controlfield = true
|
29
|
+
@controlfield = {}
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
def end_element(name)
|
34
|
+
if @in_subfield
|
35
|
+
@in_subfield = false
|
36
|
+
|
37
|
+
subfield = Document::Subfield.new(@subfield[:code], @subfield[:value])
|
38
|
+
@datafield[:subfields] << subfield
|
39
|
+
elsif @in_datafield
|
40
|
+
@in_datafield = false
|
41
|
+
|
42
|
+
datafield = Document::Datafield.new(@datafield[:tag], ind1: @datafield[:ind1], ind2: @datafield[:ind2])
|
43
|
+
@datafield[:subfields].each do |subfield|
|
44
|
+
datafield.add_subfield(subfield)
|
45
|
+
end
|
46
|
+
|
47
|
+
@document.add_datafield(datafield)
|
48
|
+
elsif @in_controlfield
|
49
|
+
@in_controlfield = false
|
50
|
+
|
51
|
+
controlfield = Document::Controlfield.new(@controlfield[:tag], @controlfield[:values])
|
52
|
+
@document.add_controlfield(controlfield)
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
def attr(name, value)
|
57
|
+
if @in_subfield
|
58
|
+
@subfield[:code] = value if name == :code
|
59
|
+
elsif @in_datafield
|
60
|
+
if name == :tag
|
61
|
+
@datafield[:tag] = value
|
62
|
+
elsif name == :ind1
|
63
|
+
@datafield[:ind1] = value
|
64
|
+
elsif name == :ind2
|
65
|
+
@datafield[:ind2] = value
|
66
|
+
end
|
67
|
+
elsif @in_controlfield
|
68
|
+
@controlfield[:tag] = value if name == :tag
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
def text(value)
|
73
|
+
if @in_subfield
|
74
|
+
@subfield[:value] = value.include?("&") ? @html_entities_coder.decode(value) : value
|
75
|
+
elsif @in_controlfield
|
76
|
+
@controlfield[:values] = value
|
77
|
+
end
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
require "active_support"
|
2
|
+
require "active_support/core_ext"
|
3
|
+
require "htmlentities"
|
4
|
+
require "ox"
|
5
|
+
|
6
|
+
module Metacrunch
|
7
|
+
require_relative "marcxml/version"
|
8
|
+
require_relative "marcxml/parser"
|
9
|
+
require_relative "marcxml/document"
|
10
|
+
|
11
|
+
class << self
|
12
|
+
#
|
13
|
+
# Convenience method for Metacrunch::Marcxml.parse
|
14
|
+
#
|
15
|
+
# @return [Metacrunch::Marcxml::Document] the parsed {Metacrunch::Marcxml::Document}
|
16
|
+
# @see Metacrunch::Marcxml#parse
|
17
|
+
#
|
18
|
+
def Marcxml(xml)
|
19
|
+
Metacrunch::Marcxml.parse(xml)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
|
24
|
+
module Marcxml
|
25
|
+
class << self
|
26
|
+
#
|
27
|
+
# Parses a MARCXML string into a {Metacrunch::Marcxml::Document}.
|
28
|
+
#
|
29
|
+
# @param xml [String] the MARCXML document as a string
|
30
|
+
# @return [Metacrunch::Marcxml::Document] the parsed {Metacrunch::Marcxml::Document}
|
31
|
+
#
|
32
|
+
def parse(xml)
|
33
|
+
Parser.new.parse(xml)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "metacrunch/marcxml/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "metacrunch-marcxml"
|
8
|
+
spec.version = Metacrunch::Marcxml::VERSION
|
9
|
+
spec.authors = ["René Sprotte"]
|
10
|
+
spec.email = "r.sprotte@ub.uni-paderborn.de"
|
11
|
+
spec.summary = %q{MARCXML package for the metacrunch ETL toolkit.}
|
12
|
+
spec.homepage = "http://github.com/ubpb/metacrunch-marcxml"
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
16
|
+
spec.bindir = "exe"
|
17
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
18
|
+
spec.require_paths = ["lib"]
|
19
|
+
|
20
|
+
spec.add_dependency "activesupport", ">= 5.1"
|
21
|
+
spec.add_dependency "htmlentities", ">= 4.3"
|
22
|
+
spec.add_dependency "ox", ">= 2.8"
|
23
|
+
end
|
24
|
+
|
metadata
ADDED
@@ -0,0 +1,104 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: metacrunch-marcxml
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 2.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- René Sprotte
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-09-27 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: activesupport
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '5.1'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '5.1'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: htmlentities
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '4.3'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '4.3'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: ox
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.8'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.8'
|
55
|
+
description:
|
56
|
+
email: r.sprotte@ub.uni-paderborn.de
|
57
|
+
executables: []
|
58
|
+
extensions: []
|
59
|
+
extra_rdoc_files: []
|
60
|
+
files:
|
61
|
+
- ".gitignore"
|
62
|
+
- ".rspec"
|
63
|
+
- ".travis.yml"
|
64
|
+
- ".yardopts"
|
65
|
+
- Gemfile
|
66
|
+
- License.txt
|
67
|
+
- Rakefile
|
68
|
+
- Readme.md
|
69
|
+
- bin/console
|
70
|
+
- lib/metacrunch/marcxml.rb
|
71
|
+
- lib/metacrunch/marcxml/document.rb
|
72
|
+
- lib/metacrunch/marcxml/document/controlfield.rb
|
73
|
+
- lib/metacrunch/marcxml/document/datafield.rb
|
74
|
+
- lib/metacrunch/marcxml/document/datafield_set.rb
|
75
|
+
- lib/metacrunch/marcxml/document/subfield.rb
|
76
|
+
- lib/metacrunch/marcxml/document/subfield_set.rb
|
77
|
+
- lib/metacrunch/marcxml/parser.rb
|
78
|
+
- lib/metacrunch/marcxml/version.rb
|
79
|
+
- metacrunch-marcxml.gemspec
|
80
|
+
homepage: http://github.com/ubpb/metacrunch-marcxml
|
81
|
+
licenses:
|
82
|
+
- MIT
|
83
|
+
metadata: {}
|
84
|
+
post_install_message:
|
85
|
+
rdoc_options: []
|
86
|
+
require_paths:
|
87
|
+
- lib
|
88
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
89
|
+
requirements:
|
90
|
+
- - ">="
|
91
|
+
- !ruby/object:Gem::Version
|
92
|
+
version: '0'
|
93
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
94
|
+
requirements:
|
95
|
+
- - ">="
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
98
|
+
requirements: []
|
99
|
+
rubyforge_project:
|
100
|
+
rubygems_version: 2.6.11
|
101
|
+
signing_key:
|
102
|
+
specification_version: 4
|
103
|
+
summary: MARCXML package for the metacrunch ETL toolkit.
|
104
|
+
test_files: []
|